© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96728
    Prev
    Next
    INDEX
    Explanations

    technology and online activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.50
    hoeddwyd
    -0.47
    fromnode
    -0.45
     grève
    -0.44
    Current
    -0.44
     насељу
    -0.42
     internet
    -0.42
    Familiar
    -0.41
     books
    -0.41
    TextAppearance
    -0.41
    POSITIVE LOGITS
     separados
    0.56
     marquées
    0.56
    UnsafeEnabled
    0.55
     nakalista
    0.55
    ozof
    0.54
    EndGlobalSection
    0.53
    dtp
    0.52
    Beskrivning
    0.52
    akhstan
    0.51
    wsgi
    0.51
    Activations Density 0.005%

    No Known Activations